Prax Lannister f6a910dec9

fix(models): normalize api_base->base_url for ChatOpenAI + warn on unknown config keys (#3790) ...

ModelConfig is `extra="allow"`, so a config key like `api_base` (which
config.example.yaml uses for other model classes, e.g. PatchedChatDeepSeek and
Moonshot) gets copied onto a `langchain_openai:ChatOpenAI` model by users.
LangChain's OpenAI client does not reject the unknown kwarg — it transfers it
into `model_kwargs` (with a UserWarning), which is then spread into every
`Completions.create()` call and rejected by the OpenAI SDK at REQUEST time with
an opaque `unexpected keyword argument 'api_base'` error. The endpoint override
is also silently dropped, so the model targets the wrong base URL.

Changes in factory.py, mirroring the existing OpenAI-compatible helpers:

- `_normalize_openai_base_url`: renames `api_base` -> `base_url` for the
  OpenAI-compatible family (ChatOpenAI + PatchedChatOpenAI); when an endpoint
  key is already present, drops the alias with a warning. Runs before the
  stream_usage/stream_chunk_timeout heuristics so they see the canonical key.
- `_warn_unknown_model_settings`: scoped to the same OpenAI-compatible family
  (where the model_kwargs divert-and-crash actually happens and the field/alias
  set is accurate), logs an actionable warning for unrecognized config keys.
- The three OpenAI-compatible helpers now share `_OPENAI_COMPAT_USE_PATHS`
  instead of disagreeing on the literal class string.

Adds a note to docs/CONFIGURATION.md and 9 tests covering normalization
(ChatOpenAI + PatchedChatOpenAI, both-set precedence for base_url and
openai_api_base, non-OpenAI class untouched, no-op when unset) and the
unknown-key warning (fires on a typo, silent on a clean config and on
non-OpenAI providers like ChatAnthropic).

2026-07-05 10:17:25 +08:00

..

harness

fix(models): normalize api_base->base_url for ChatOpenAI + warn on unknown config keys (#3790)

2026-07-05 10:17:25 +08:00